5 papers
Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion
Kazuma Fujiwara, Takuya Funatomi, Kazuya Kitano +2
Snapshot hyperspectral imaging avoids sequential scanning, but systems that jointly achieve stable reconstruction, low cost, and compact optics remain limited. We present a snapsho…
WildSplatter: Feed-forward 3D Gaussian Splatting with Appearance Control from Unconstrained Images
Yuki Fujimura, Takahiro Kushida, Kazuya Kitano +2
We propose WildSplatter, a feed-forward 3D Gaussian Splatting (3DGS) model for unconstrained images with unknown camera parameters and varying lighting conditions. 3DGS is an effec…
UFV-Splatter: Pose-Free Feed-Forward 3D Gaussian Splatting Adapted to Unfavorable Views
Yuki Fujimura, Takahiro Kushida, Kazuya Kitano +2
This paper presents a pose-free, feed-forward 3D Gaussian Splatting (3DGS) framework designed to handle unfavorable input views. A common rendering setup for training feed-forward…
NLOS-NeuS: Non-line-of-sight Neural Implicit Surface
Yuki Fujimura, Takahiro Kushida, Takuya Funatomi +1
Non-line-of-sight (NLOS) imaging is conducted to infer invisible scenes from indirect light on visible objects. The neural transient field (NeTF) was proposed for representing scen…
Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariance
Yuki Fujimura, Masaaki Iiyama, Takuya Funatomi +1
We propose a learning-based depth from focus/defocus (DFF), which takes a focal stack as input for estimating scene depth. Defocus blur is a useful cue for depth estimation. Howeve…